Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3860. Min Act: -0.0001

Data Index: 983068 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1227452 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4546. Min Act: -0.0001

Data Index: 320045 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3348. Min Act: -0.0000

Data Index: 393167 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1095069 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3766. Min Act: -0.0001

Data Index: 835091 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3402. Min Act: -0.0001

Data Index: 619228 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3809. Min Act: -0.0001

Data Index: 189092 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3503. Min Act: -0.0001

Data Index: 1308411 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3503. Min Act: -0.0001

Data Index: 304696 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2982. Min Act: -0.0001

Data Index: 871028 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3051. Min Act: -0.0000

Data Index: 332999 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3282. Min Act: -0.0001

Data Index: 831646 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3043. Min Act: -0.0001

Data Index: 830602 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3188. Min Act: -0.0000

Data Index: 864176 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3168. Min Act: -0.0001

Data Index: 754470 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1066376 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2995. Min Act: -0.0000

Data Index: 553035 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1301918 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2963. Min Act: -0.0000

Data Index: 576335 (C4 (Web Text))

Max Activating Token Index: 30